scanned-pdf

Get clean data from tricky documents, powered by vision-language models ⚡

A self-hosted PDF OCR API that converts scanned documents to markdown. Powered by PaddleOCR-VL, runs on GPU via Docker.

Pdf utilities for text extraction in digital and convert scanned pdf into canvas.

Scanned PDFs, web pages and broken EPUBs → one clean, reflowable EPUB3 that passes official epubcheck at zero errors. Apple Vision OCR on your own Mac — and the OCR ships as its own CLI. 100% offline, no API key, MIT.

为PDF格式的电子书生成目录。通过多模态AI实现，自动生成有层次的目录书签。专为扫描版/纯图片PDF设计。 Generate a table of contents for PDF ebooks via multimodal AI. Auto-produces hierarchical bookmarks. Designed for scanned / image-only PDFs.

Open-source OCR app for Linux. Extract editable text from scanned PDFs, photos and images with Tesseract, translate it and export to .txt. Python/PyQt5, MIT.

Lightweight bash script to convert scanned PDFs into searchable, copyable PDFs using Tesseract OCR with parallel processing.

Medical OCR refinement pipeline for Codex / 医学文本OCR Skill

Convert Word/Excel/PowerPoint to PDF with custom watermarks and non-editable scanned output. 100% offline & private - documents never leave your PC. Free, no account.

Extract selectable Bengali (Bangla) text from scanned/image PDFs using PaddleOCR-VL-1.6 on GPU — outputs plain text, page by page, with resume support.

Outil OCR permettant d’extraire et de structurer du texte à partir d’images et de PDF scannés (export en .docx et .txt) — prise en charge du français et de l’anglais

Free private browser PDF tools for compression, scanned documents, merging, splitting and conversion. No document upload or account.